Mid-level AI Engineer

Join our team as a Mid-level AI Engineer and help drive the next generation of GenAI-powered applications. You will architect robust solutions, collaborating closely with fellow engineers, product managers, and designers to turn cutting-edge research into real-world impact. If you thrive in a fast-paced, innovation-driven environment and are passionate about clear communication, this is the opportunity for you.

Responsibilities:

• Build GenAI applications such as question-answering systems, content generation tools, and extraction pipelines.
• Design, implement, and optimize RAG pipelines end-to-end: ingestion, chunking, embedding, prompt templating, evaluation, and deployment.
• Develop robust APIs using Python frameworks (FastAPI preferred).
• Work with multiple LLMs (OpenAI, Mistral, Anthropic, etc.) and evaluate model performance for different use cases.
• Use LangChain, LangGraph, or LangSmith to orchestrate and monitor GenAI workflows.
• Deploy applications on AWS or Azure and implement CI/CD for continuous improvement.
• Collaborate with data engineers and product managers to translate technical designs into scalable solutions.
• Participate in system design discussions, contributing ideas for performance and maintainability.

Must-have Skills:

• Python: Strong experience with the language. Able to design clean, modular, production-grade code.
• API Development: Proven experience building and maintaining APIs (FastAPI/Flask).
• GenAI Stack: LangChain, LangGraph, LangSmith; multiple LLM APIs (OpenAI, Mistral, etc.).
• RAG Lifecycle: Data ingestion, prompt templating (Jinja), evaluation/re-ranking, deployment.
• Cloud/DevOps: Hands-on with AWS or Azure (deployments, monitoring).

Good-to-have Skills:

• Understanding of distributed systems and scaling strategies.
• Experience with containerization (Docker) and orchestration (Kubernetes).
• Familiarity with Guardrails AI or Responsible AI frameworks.
• Basic UI integration knowledge (React, optional).